{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T21:51:39Z","timestamp":1730238699773,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T00:00:00Z","timestamp":1699488000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T00:00:00Z","timestamp":1699488000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,11,9]]},"DOI":"10.1109\/icdl55364.2023.10364556","type":"proceedings-article","created":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T19:40:19Z","timestamp":1703533219000},"page":"133-138","source":"Crossref","is-referenced-by-count":0,"title":["Real-World Robot Control and Data Augmentation by World-Model Learning from Play"],"prefix":"10.1109","author":[{"given":"Yuta","family":"Nomura","sequence":"first","affiliation":[{"name":"Graduate School of Integrated Design Engineering, Keio University,Kanagawa,Japan"}]},{"given":"Shingo","family":"Murata","sequence":"additional","affiliation":[{"name":"Graduate School of Integrated Design Engineering, Keio University,Kanagawa,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aax8177"},{"key":"ref4","first-page":"983","article-title":"Robustness via retrying: Closed-loop robotic manipulation with self-supervised learning","volume-title":"Conference on robot learning","author":"Ebert","year":"2018"},{"key":"ref5","first-page":"1113","article-title":"Learning latent plans from play","volume-title":"Conference on robot learning","author":"Lynch","year":"2020"},{"key":"ref6","article-title":"From play to policy: Conditional behavior generation from uncurated robot data","volume-title":"International Conference on Learning Representations","author":"Cui","year":"2023"},{"key":"ref7","article-title":"Latent plans for task agnostic offline reinforcement learning","volume-title":"Proceedings of the 6th Conference on Robot Learning (CoRL)","author":"Rosete-Beas","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.061"},{"key":"ref9","first-page":"2451","article-title":"Recurrent world models facilitate policy evolution","volume-title":"Advances in Neural Information Processing Systems 31","author":"Ha","year":"2018"},{"key":"ref10","article-title":"Learning latent dynamics for planning from pixels","volume-title":"International Conference on Machine Learning","author":"Hafner","year":"2019"},{"key":"ref11","first-page":"1025","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","volume-title":"Conference on Robot Learning","volume":"100","author":"Gupta","year":"2020"},{"key":"ref12","article-title":"Demonstration-bootstrapped autonomous practicing via multi-task reinforcement learning","author":"Gupta","year":"2022","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"1424","article-title":"Plato: Predicting latent affordances through object-centric play","volume-title":"Conference on Robot Learning","author":"Belkhale","year":"2023"},{"key":"ref14","article-title":"Mimicplay: Long-horizon imitation learning by watching human play","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Learning to play by imitating humans","author":"Dinyari","year":"2020","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Mastering atari with discrete world models","volume-title":"International Conference on Learning Representations","author":"Hafner","year":"2021"},{"key":"ref17","article-title":"Transformers are sample-efficient world models","volume-title":"International Conference on Learning Representations","author":"Micheli","year":"2023"},{"key":"ref18","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487173"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-73003-5_196"},{"key":"ref21","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2023 IEEE International Conference on Development and Learning (ICDL)","start":{"date-parts":[[2023,11,9]]},"location":"Macau, China","end":{"date-parts":[[2023,11,11]]}},"container-title":["2023 IEEE International Conference on Development and Learning (ICDL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10364334\/10364349\/10364556.pdf?arnumber=10364556","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T21:17:33Z","timestamp":1705094253000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10364556\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,9]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icdl55364.2023.10364556","relation":{},"subject":[],"published":{"date-parts":[[2023,11,9]]}}}